Alibaba / Qwen, released Feb 15, 2026

Qwen3.5 397B-A17Bprice, context, benchmarks and release details

Provisional: not enough results to rank yet Open weights 69% confidence 69 percent, Medium confidence, 3 of 7 expected sources in
64.0
SI Score
#39 of 142 ranked models
Input, per 1M tokens
$0.17Alibaba Model Studio pricingOfficial Alibaba Model Studio Global USD on-demand API; 0<Token≤128K; . Output uses non-thinking rate when both modes are available; thinking-only products use their thinking rate. Cache, Batch, free quotas and regional rates excluded Retrieved Oct 9, 2026 · factual citation
Open source ↗
Output, per 1M tokens
$1.03Alibaba Model Studio pricingOfficial Alibaba Model Studio Global USD on-demand API; 0<Token≤128K; . Output uses non-thinking rate when both modes are available; thinking-only products use their thinking rate. Cache, Batch, free quotas and regional rates excluded Retrieved Oct 9, 2026 · factual citation
Open source ↗
Context window
262Kmodels.devPublished source fact Retrieved Oct 9, 2026 · MIT
Open source ↗
Max output
65.5Kmodels.devPublished source fact Retrieved Oct 9, 2026 · MIT
Open source ↗
Released
Feb 15, 2026models.devPublished source fact Retrieved Oct 9, 2026 · MIT
Open source ↗

How the score breaks down

Coding (weight 40 percent) 76.4
Math (weight 15 percent) 48.8
Preference (weight 15 percent) 76.7
Reasoning (weight 30 percent) 86.1

Weights: reasoning 30%, math 15%, coding 40%, preference 15%. Results use fixed 0–100 scales before averaging, and thin evidence is pulled toward 50. Method si-v3-retained-evidence-2, computed Oct 9, 2026, 05:13 UTC.

Around it on the leaderboard

  1. 37 Grok 4.5 64.8
  2. 38 Kimi K2.6 64.0
  3. 39 Qwen3.5 397B-A17B 64.0
  4. 40 GPT-5.5 Pro 63.5
  5. 41 GPT-5.6 Luna 63.4

Full leaderboard

Benchmark results

5 benchmarks, 8 results

Each row shows the best published result. Where a model was tested at several settings, such as reasoning effort, open the row to see each one. Hover or tap a value for its source.

GPQA Diamondreasoning 86.4%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] nonePublished Aug 7, 2026 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 86.4 2 settings
  • no reasoning 86.4%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] nonePublished Aug 7, 2026 Retrieved Oct 9, 2026 · CC-BY
    Open source ↗
  • Setting 2 85.9%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] Published Aug 7, 2026 Retrieved Oct 9, 2026 · CC-BY
    Open source ↗
About GPQA Diamond
FrontierMath Tiers 1–3 (v2)math 31.2%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] nonePublished Aug 30, 2026 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 31.2 2 settings
  • no reasoning 31.2%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] nonePublished Aug 30, 2026 Retrieved Oct 9, 2026 · CC-BY
    Open source ↗
  • Setting 2 29.5%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] Published Aug 28, 2026 Retrieved Oct 9, 2026 · CC-BY
    Open source ↗
About FrontierMath Tiers 1–3 (v2)
OTIS Mock AIME 2024–2025math 88.9%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] Published Aug 7, 2026 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 88.9 2 settings
  • no reasoning 82.2%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] nonePublished Aug 7, 2026 Retrieved Oct 9, 2026 · CC-BY
    Open source ↗
  • Setting 2 88.9%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] Published Aug 7, 2026 Retrieved Oct 9, 2026 · CC-BY
    Open source ↗
About OTIS Mock AIME 2024–2025
SWE-bench Verifiedcoding 76.4%Official model cards via models.devLab-reported; metric resolved; transcribed by MIT models.dev catalog; not independently evaluated [variant] Retrieved Oct 9, 2026 · factual citation; MIT transcription
Open source ↗ 76.4
LMArena Textpreference 1437.9 eloLMArena / ArenaPublished source fact [variant] text / overallPublished Oct 8, 2026 Retrieved Oct 9, 2026 · CC-BY-4.0
Open source ↗ 76.7

Normalization uses a fixed 0–100 scale for each unit, independent of other models. Compare evaluation conditions before reading a small gap as decisive. “Lab-reported” marks the provider's own published figure.

Details and sources

Open weights
Yesmodels.devPublished source fact Retrieved Oct 9, 2026 · MIT
Open source ↗
License
not yet reported
Input modalities
text, image, video, audiomodels.devPublished source fact Retrieved Oct 9, 2026 · MIT
Open source ↗
First seen by SuperIndex
Oct 8, 2026
Coverage
55% of expected source weight

Reported (3)

  • Epoch AI BenchmarkingOct 8, 2026
  • Official model cards via models.devOct 8, 2026
  • LMArena / ArenaOct 8, 2026

Awaiting (4)

  • ARC Prize13% of weight
  • Humanity’s Last Exam13% of weight
  • LiveBench13% of weight
  • Terminal-Bench6% of weight

Confidence rises as pending sources publish. Some sources never cover some models, so confidence reaches 100% at 80% of expected weight.

What changed

All releases · RSS feed

Alerts on this device

What to be alerted about
RSS feed